Bing Chat: The Future of Search Engines?
Bibliographic record
Abstract
ABSTRACT Introduced by Microsoft in February 2023, Bing Chat is a feature of the Bing search engine that integrates an OpenAI large language model (LLM) customised for search (Mehdi, 2023a). This poster compares the outputs of Bing Chat and a standard existing search engine (DuckDuckGo) in response to identical keyword queries and corresponding natural language (NL) questions. Specifically, we examined: (1) the length of Bing Chat's responses and DuckDuckGo's first page of search results, by number of website links; and, (2) the length of Bing Chat's textual summaries, by number of website links. We found that, on average, significantly fewer websites were linked to in Bing Chat's responses compared to DuckDuckGo's search results. Our findings have important implications for website operators, who may receive less traffic and ad revenue if LLM‐enabled search engines are widely adopted in the future. Human‐Computer Interaction (HCI) will inevitably face the need for more research on human information behaviours adaptations in response to the changing search paradigm.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.032 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.007 | 0.017 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".